Abstract: Systems and methods for determining a mapping between activities are provided. One or more prompts defining 1) instructions and 2) activities executed during one or more instances of execution of a process are received. A mapping between one or more activities extracted from a process model of the process and one or more of the activities executed during the one or more instances of execution is determined using a large language model based on the instructions. The mapping is output.

Abstract: Systems and methods for determining whether activity names of a process satisfy a validation criteria are provided. One or more prompts defining 1) instructions, 2) activity name validation criteria, and 3) activity names of a process are received. It is determined whether the activity names satisfy the validation criteria using a large language model based on the instructions. Results of the determining are output.

Abstract: Systems and methods for generating names for portions, such as, e.g., subprocesses or variants, of a process model are provided. One or more prompts defining 1) instructions, 2) a textual description of a process model of a process, and 3) one or more portions of the process model are received. A name for each of the one or more portions of the process model is generated using a large language model based on the instructions. The name for each of the one or more portions of the process model is output.

Abstract: Systems and methods for generating a description of non-conformance using a large language model are provided. One or more prompts defining 1) instructions, 2) a textual description of a process model of a process, and 3) an instance of execution of the process are received. A description of non-conformance of the instance of execution to the process model is generated using a large language model based on the textual description of the process model and the instructions. The description of the non-conformance of the instance of execution to the process model is output.

Abstract: Systems and methods for generating a natural language representation of one or more steps to be performed by one or more RPA (robotic process automation) robots for performing an activity are provided. One or more prompts defining 1) instructions, 2) a description of a process, 3) a name of a source system from which the process was extracted, and 4) a name of an activity of the process are received. A natural language representation of one or more steps to be performed by one or more RPA (robotic process automation) robots for performing the activity is performed using a large language model based on the instructions, the description of the process, the name of the source system, and the name of the activity. The natural language representation of the one or more steps to be performed by the one or more RPA robots for performing the activity is output.

Abstract: Process evolution for robotic process automation (RPA) and RPA workflow micro-optimization are disclosed. Initially, an RPA implementation may be scientifically planned, potentially using artificial intelligence (AI). Embedded analytics may be used to measure, report, and align RPA operations with strategic business outcomes. RPA may then be implemented by deploying AI skills (e.g., in the form of machine learning (ML) models) through an AI fabric that seamlessly applies, scales, manages AI for RPA workflows of robots. This cycle of planning, measuring, and reporting may be repeated, potentially guided by more and more AI, to iteratively improve the effectiveness of RPA for a business. RPA implementations may also be identified and implemented based on their estimated return on investment (ROI).

Abstract: Systems and methods for object centric process mining are provided. Execution data of a process having a plurality of entities is received. A plurality of object networks representing relationships between objects of the plurality of entities are generated based on the execution data. A set of transitions is determined for each of the plurality of object networks. A process graph of execution of the process is generated based on the sets of transitions. The process graph is output.

Abstract: Dynamically updating, or retraining and updating, artificial intelligence (AI)/machine learning (ML) models in digital processes at runtime is disclosed. Production operation may not need to be stopped for AI/ML model update or retraining and update. The update steps and/or retraining steps for the AI/ML model may be included as part of the digital process. The AI/ML model update may be requested from internal logic (e.g., from the evaluation of a condition, by an expression that calls for the AI/ML model, etc.), external requests (e.g., from external triggers in a finite state machine (FSM), such as a file change, database data, a service call, etc.), or both. Automation of AI/ML model updates or retraining and updates may be provided, where the software reloads/reinitializes/re-instantiates with a retrained and/or updated AI/ML model after (and possibly immediately after) the AI/ML model becomes available.

Abstract: Using a cognitive artificial intelligence (AI) layer (e.g., a generative AI model and one or more other AI/ML models) to perform robotic process automation (RPA) robot repair is disclosed. Computer vision (CV) and/or optical character recognition (OCR) models may be called by RPA robots when performing activities in RPA workflows to identify graphical elements and text, respectively, in a user interface (UI). However, the CV or OCR model may not find a graphical element or text targeted by the activity of the RPA workflow, or the RPA robot may encounter an exception and otherwise fail when performing the activity. In such cases, a cognitive AI layer including a generative AI model may be used to find the target graphical element or text, or to address the robot failure.

Abstract: A method executed by a fallback engine is provided. The fallback engine is implemented as a computer program within a computing system. The method includes tracking information for versions for a selector stored in a selector repository. The information includes a proof of work defining an amount of use per version of the versions. The method includes determining a current state of an original selector version of the selector utilized by an automation and automatically implementing a fallback operation that updates a target of the selector of the automation from the original selector version to a different selector version based the proof of work for the different selector version in the selector repository.

Abstract: A method for translating an unstructured existing process into a well-structured process model is provided. The method is executed by a generation engine implemented as a computer program within a computing environment. The method includes analyzing elements or relationships of the unstructured existing process to detect model violations. The model violations include when the elements or the relationships fail at least one model requirement.

Abstract: Automatic data transfer between a source and a target using semantic artificial intelligence (AI) for robotic process automation (RPA) is disclosed. A user may be provided with the option of selecting a source and a target and indicating through an intuitive user interface that he or she would like to copy data from the source to the destination, regardless of format. This may be done at design time or at run time. For instance, the source and/or target may be a web page, a graphical user interface (GUI) of an application, an image, a file explorer, a spreadsheet, a relational database, a flat file source, any other suitable format, or any combination thereof. The source and the target may have different formats. The source, target, or both may not necessarily be visible to the user.

Abstract: Systems and methods for allocating computing environments for completing an RPA (robotic process automation) workload are provided. A request for completing an RPA workload is received. A number of computing environments to allocate for completing the RPA workload is calculated based on a selected one of a plurality of RPA autoscaling strategies. The calculated number of computing environments is allocated for allocating one or more RPA robots to complete the RPA workload. The computing environments may be virtual machines.

Abstract: A method is provided. The method is executed by an autocomplete prediction engine implemented as a computer program within a computing environment. The autocomplete prediction engine executes automated communication mining on a communication. The method includes processing the communication to extract intents and entities related to each intent. The method includes providing the intents and the entities into forms using a language model to provide a conversational or natural language understanding of the communication.

Abstract: Target-based schema identification and semantic mapping for robotic process automation (RPA) are disclosed. When looking at a source, such as a document, a web form, a user interface of a software application, a data file, etc., it is often difficult for software to determine which fields are labels and which are values associated with those labels. Since values have not yet been entered for various labels (e.g., first name, company, customer number, etc.), these labels are easier to detect than when the target also includes various values associated with the labels. A selection of an empty target may be received and target-based schema identification may be performed on the empty target, determining labels and a type of the target. Semantic matching may then be performed between a source and the target. These features may be performed at design time or runtime.

Abstract: A method is provided. The method is executed by an autocomplete prediction engine implemented as a computer program within a computing environment. The autocomplete prediction engine executes automated communication mining on a communication. The method includes processing the communication to extract intents and entities related to each intent. The method includes providing the intents and the entities into forms using a language model to provide a conversational or natural language understanding of the communication.

Abstract: Using generative AI to supplement automated information extraction is disclosed. Computer vision (CV) and/or optical character recognition (OCR) models and a generative artificial intelligence (AI) model are used together to extract information (e.g., names, dates, invoice numbers, etc.) from a source. Acceptance threshold(s) may be used to accept predictions for extracted data elements from the models, and the prediction from the generative AI model may be preferred or a human may be tasked with reviewing the element. If no model meets its respective acceptance threshold (whether common or specific to that model), these element(s) may be marked for subsequent human review, or a human can be looped in to correct these element(s). The models may then be retrained using these labeled elements.

Abstract: Systems and methods for instantiating a filter for a process graph are provided. A process graph of a workflow is received. Context data associated with the process graph is stored. A filter is instantiated to filter the process graph based on the stored context data. The filtered process graph is output.

Abstract: Systems and methods for configuring an RPA (robotic process automation) platform to perform a candidate process automation are provided. Discovery data relating to a candidate process automation is generated. RPA platform design components for configuring an RPA platform to perform the candidate process automation are generated based on the discovery data. The RPA platform is configured based on the RPA platform design components.

Abstract: Automation windows for robotic process automation (RPA) using multiple desktops are disclosed. One or more robot desktops are launched, and one or more RPA robots operate in the robot desktop(s). The robot desktops may not initially be the active desktop. When the robot(s) execute their automations, if an activity in the RPA robot workflow needs the robot desktop to be the active desktop, the active desktop is switched to the appropriate robot desktop when the appropriate robot desktop is not already active, and activit(ies) of the RPA workflow that require the robot desktop to be the active desktop are executed. In some embodiments, after RPA workflow execution finishes, the robot desktop, the RPA robot, or both, are automatically closed.